🚀 𝗥𝗘𝗦𝗧 𝗶𝗻 𝗣𝗲𝗮𝗰𝗲 - 𝗪𝗵𝘆 𝗟𝗟𝗠𝘀 𝗖𝗮𝗻'𝘁 𝗖𝗥𝗨𝗗: 𝗔 𝗥𝗲𝗳𝗹𝗲𝗰𝘁𝗶𝗼𝗻

🚀 𝗥𝗘𝗦𝗧 𝗶𝗻 𝗣𝗲𝗮𝗰𝗲 - 𝗪𝗵𝘆 𝗟𝗟𝗠𝘀 𝗖𝗮𝗻’𝘁 𝗖𝗥𝗨𝗗: 𝗔 𝗥𝗲𝗳𝗹𝗲𝗰𝘁𝗶𝗼𝗻

Yesterday I was listening to a talk by Martin Sakowski and Martin Karrer “REST in Peace - Why LLMs Can’t CRUD” which sparked a lot of interesting discussion. 💭

🤖 They observed that even with the rise of MCP, AI Agents often struggle to master their given tasks reliably, consistently, and in an efficient way—driving costs and potentially failing projects.

🤔 𝗪𝗵𝘆 𝗶𝘀 𝘁𝗵𝗶𝘀 𝗵𝗮𝗽𝗽𝗲𝗻𝗶𝗻𝗴?

They analyzed a seemingly simple use case: booking a meeting. We’ve all been there—it’s a mess to get everyone on one page. But even if we leave humans out of the loop, it’s still complicated!

📝 Today’s APIs are created to be consumed by developers. For some reason, developers are able and willing to deal with poor APIs. In their example, the Martins assumed a simple CRUD API and counted 20-50 API invocations for a simple agenda cleaning activity. Each can fail for many reasons. So do the agents.

🛠️ 𝗪𝗵𝗮𝘁’𝘀 𝘁𝗵𝗲 𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻?

APIs need to be designed working backwards from the needs of the API consumers. The Martins argued that intent-based APIs would be much more reliable and efficient for agents to use—and they demonstrated this with their use case.

💡 It’s important to have the consumer (in this case an AI agent) in mind while designing an API. Only then can you ensure your AI agent will work reliably and cost-efficiently. The current proposal is to not just provide MCP implementation based on existing (likely poor) APIs but also invest in building rich, intent-based APIs.

🔄 𝗧𝗵𝗲 𝗜𝗿𝗼𝗻𝘆

I think this makes sense. But there’s still a lot of irony here (which I partly ranted about in my first MCP post [1]). We never cared enough about DX (developer experience) to build good APIs. The technology exists—RESTful APIs using hypermedia can be built in an intent-based way. Nothing new here. We simply never did it.

❓ 𝗪𝗵𝘆?

I think yesterday I understood why. Many developers, for some reason, happily take on all the tinkering work, so they never invested in improving this. But more importantly, from a business perspective, this cost wasn’t transparent. Software development has a cost, but it’s a one-off at build time.

With AI agents, we’ve shifted this effort to run-time. Agents repeat the work on every call, driving up costs and increasing the likelihood of failure. Hence, we care now. It’s become business-critical.

🌟 𝗧𝗵𝗲 𝗦𝗶𝗹𝘃𝗲𝗿 𝗟𝗶𝗻𝗶𝗻𝗴

As a tech person, I like this because we can finally focus on building the right thing. AI agents will likely help us; observing and gathering execution information will help focus efforts on relevant APIs.

𝗪𝗵𝗮𝘁’𝘀 𝘆𝗼𝘂𝗿 𝘃𝗶𝗲𝘄?  𝗗𝗼 𝘆𝗼𝘂 𝘁𝗵𝗶𝗻𝗸 𝗠𝗖𝗣 𝗶𝘀 𝗴𝗼𝗼𝗱 𝗲𝗻𝗼𝘂𝗴𝗵?  𝗠𝗮𝘆𝗯𝗲 𝘆𝗼𝘂’𝗿𝗲 𝗱𝗼𝗶𝗻𝗴 𝗥𝗘𝗦𝗧𝗳𝘂𝗹 𝗔𝗣𝗜𝘀 𝘁𝗵𝗲 𝗿𝗶𝗴𝗵𝘁 𝘄𝗮𝘆, 𝗯𝗿𝗲𝗲𝘇𝗶𝗻𝗴 𝘁𝗵𝗿𝗼𝘂𝗴𝗵 𝗛𝗔𝗧𝗘𝗢𝗔𝗦 𝗮𝗻𝗱 𝗱𝗼𝗻’𝘁 𝘀𝗲𝗲 𝗮𝗻𝘆 𝗻𝗲𝗲𝗱 𝘁𝗼 𝗰𝗵𝗮𝗻𝗴𝗲?